Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

TAPD 单据开发助手 — measured AI agent skill | DecimalAI

tencentblueking/bk-monitor-tapd-dev

NewSkillScoreMaintained

根据 TAPD 单据分析开发需求并生成方案。当用户需要开发 TAPD 需求/缺陷/任务时使用。

productivityby tencentblueking

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/tencentblueking-bk-monitor-tapd-dev/SKILL.md

decimalai skills pull tencentblueking-bk-monitor-tapd-dev --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/tencentblueking-bk-monitor-tapd-dev/SKILL.md https://app.decimal.ai/s/tencentblueking-bk-monitor-tapd-dev/SKILL.md

Raw file: /s/tencentblueking-bk-monitor-tapd-dev/SKILL.md ↗ · machine-readable summary at /s/tencentblueking-bk-monitor-tapd-dev.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

—-19% tokens0% turns87% of whole cases pass with skill (20/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-09	✗→✓	▲ Improved	14%	0%
case-04	✗→✓	▲ Improved	1%	0%
case-06	✗→✓	▲ Improved	-37%	0%
case-10	✗→✓	▲ Improved	-22%	0%
case-11	✗→✓	▲ Improved	-1%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

tencentblueking / bk-bcs

bcs-services/bcs-project-manager/.cursor/skills/bk-monitor-tapd-dev/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1

Skill contents

SKILL.md

TAPD 单据开发助手

工作流程

Step 1: 获取 TAPD ID 并验证分支（阻塞）

获取 ID：用户提供或从分支名提取（git branch --show-current，匹配 #(\d+)）
验证分支是否包含该 ID

匹配 → 继续
不匹配 → 询问用户选择（创建分支/继续开发）

Step 2-3: 获取单据

解析 workspace_id = id.substring(2, 10)
调用 MCP（stories_get、bugs_get、tasks_get）获取单据详情和评论

Step 4-6: 分析与开发

分析需求（标题、描述、评论、截止日期）
按 dev-plan-template.md 生成方案
等待用户确认后开始开发

注意事项

分支验证是第一优先级
方案需用户确认才能开始开发
评论与描述冲突时以最新评论为准

📦 可用资源

skill://bk-monitor-tapd-dev/references/branch-workflow.md
skill://bk-monitor-tapd-dev/references/dev-plan-template.md
skill://bk-monitor-tapd-dev/references/mcp-calls.md
skill://bk-monitor-tapd-dev/references/tapd-mcp-guide.md

📦 可用资源

skill://bk-monitor-tapd-dev/references/branch-workflow.md
skill://bk-monitor-tapd-dev/references/dev-plan-template.md
skill://bk-monitor-tapd-dev/references/mcp-calls.md
skill://bk-monitor-tapd-dev/references/tapd-mcp-guide.md

> 根据 SKILL.md 中的 IF-THEN 规则判断是否需要加载

Want to see if tencentblueking/bk-monitor-tapd-dev would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.